Roleplay Simulation on Humanual-Email
51.4Primary Metric
OSIM 8B
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.06 | 51.4 | |
2026.06 | 50.4 | |
2026.06 | 50.1 | |
2026.06 | 47.9 | |
2026.06 | 46.9 | |
2026.06 | 43.7 | |
2026.06 | 42.8 | |
2026.06 | 26.4 | |
2026.06 | 22.3 |
OSIM 8B
| Method | Links | |
|---|---|---|
2026.06 | 51.4 | |
2026.06 | 50.4 | |
2026.06 | 50.1 | |
2026.06 | 47.9 | |
2026.06 | 46.9 | |
2026.06 | 43.7 | |
2026.06 | 42.8 | |
2026.06 | 26.4 | |
2026.06 | 22.3 |